2385eb0c5f
This function reacquires the rtnl_lock() which is already held by
nf_unregister_hook().
This can be triggered via: modprobe nf_conntrack_ipv4 && rmmod nf_conntrack_ipv4
[ 720.628746] INFO: task rmmod:3578 blocked for more than 120 seconds.
[ 720.628749] Not tainted 4.2.0-rc2+ #113
[ 720.628752] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 720.628754] rmmod D ffff8800ca46fd58 0 3578 3571 0x00000080
[...]
[ 720.628783] Call Trace:
[ 720.628790] [<ffffffff8152ea0b>] schedule+0x6b/0x90
[ 720.628795] [<ffffffff8152ecb3>] schedule_preempt_disabled+0x13/0x20
[ 720.628799] [<ffffffff8152ff55>] mutex_lock_nested+0x1f5/0x380
[ 720.628803] [<ffffffff81462622>] ? rtnl_lock+0x12/0x20
[ 720.628807] [<ffffffff81462622>] ? rtnl_lock+0x12/0x20
[ 720.628812] [<ffffffff81462622>] rtnl_lock+0x12/0x20
[ 720.628817] [<ffffffff8148ab25>] nf_queue_nf_hook_drop+0x15/0x160
[ 720.628825] [<ffffffff81488d48>] nf_unregister_net_hook+0x168/0x190
[ 720.628831] [<ffffffff81488e24>] nf_unregister_hook+0x64/0x80
[ 720.628837] [<ffffffff81488e60>] nf_unregister_hooks+0x20/0x30
[...]
Moreover, nf_unregister_net_hook() should only destroy the queue for this
netns, not for every netns.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Fixes: 085db2c045
("netfilter: Per network namespace netfilter hooks.")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
490 lines
11 KiB
C
490 lines
11 KiB
C
/* netfilter.c: look after the filters for various protocols.
|
|
* Heavily influenced by the old firewall.c by David Bonn and Alan Cox.
|
|
*
|
|
* Thanks to Rob `CmdrTaco' Malda for not influencing this code in any
|
|
* way.
|
|
*
|
|
* Rusty Russell (C)2000 -- This code is GPL.
|
|
* Patrick McHardy (c) 2006-2012
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/netfilter.h>
|
|
#include <net/protocol.h>
|
|
#include <linux/init.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/module.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/if.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/netfilter_ipv6.h>
|
|
#include <linux/inetdevice.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/slab.h>
|
|
#include <net/net_namespace.h>
|
|
#include <net/sock.h>
|
|
|
|
#include "nf_internals.h"
|
|
|
|
static DEFINE_MUTEX(afinfo_mutex);
|
|
|
|
const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
|
|
EXPORT_SYMBOL(nf_afinfo);
|
|
const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly;
|
|
EXPORT_SYMBOL_GPL(nf_ipv6_ops);
|
|
|
|
DEFINE_PER_CPU(bool, nf_skb_duplicated);
|
|
EXPORT_SYMBOL_GPL(nf_skb_duplicated);
|
|
|
|
int nf_register_afinfo(const struct nf_afinfo *afinfo)
|
|
{
|
|
mutex_lock(&afinfo_mutex);
|
|
RCU_INIT_POINTER(nf_afinfo[afinfo->family], afinfo);
|
|
mutex_unlock(&afinfo_mutex);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_register_afinfo);
|
|
|
|
void nf_unregister_afinfo(const struct nf_afinfo *afinfo)
|
|
{
|
|
mutex_lock(&afinfo_mutex);
|
|
RCU_INIT_POINTER(nf_afinfo[afinfo->family], NULL);
|
|
mutex_unlock(&afinfo_mutex);
|
|
synchronize_rcu();
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_unregister_afinfo);
|
|
|
|
#ifdef HAVE_JUMP_LABEL
|
|
struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
|
|
EXPORT_SYMBOL(nf_hooks_needed);
|
|
#endif
|
|
|
|
static DEFINE_MUTEX(nf_hook_mutex);
|
|
|
|
static struct list_head *find_nf_hook_list(struct net *net,
|
|
const struct nf_hook_ops *reg)
|
|
{
|
|
struct list_head *nf_hook_list = NULL;
|
|
|
|
if (reg->pf != NFPROTO_NETDEV)
|
|
nf_hook_list = &net->nf.hooks[reg->pf][reg->hooknum];
|
|
else if (reg->hooknum == NF_NETDEV_INGRESS) {
|
|
#ifdef CONFIG_NETFILTER_INGRESS
|
|
if (reg->dev && dev_net(reg->dev) == net)
|
|
nf_hook_list = ®->dev->nf_hooks_ingress;
|
|
#endif
|
|
}
|
|
return nf_hook_list;
|
|
}
|
|
|
|
int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
|
|
{
|
|
struct list_head *nf_hook_list;
|
|
struct nf_hook_ops *elem, *new;
|
|
|
|
new = kzalloc(sizeof(*new), GFP_KERNEL);
|
|
if (!new)
|
|
return -ENOMEM;
|
|
|
|
new->hook = reg->hook;
|
|
new->dev = reg->dev;
|
|
new->owner = reg->owner;
|
|
new->priv = reg->priv;
|
|
new->pf = reg->pf;
|
|
new->hooknum = reg->hooknum;
|
|
new->priority = reg->priority;
|
|
|
|
nf_hook_list = find_nf_hook_list(net, reg);
|
|
if (!nf_hook_list) {
|
|
kfree(new);
|
|
return -ENOENT;
|
|
}
|
|
|
|
mutex_lock(&nf_hook_mutex);
|
|
list_for_each_entry(elem, nf_hook_list, list) {
|
|
if (reg->priority < elem->priority)
|
|
break;
|
|
}
|
|
list_add_rcu(&new->list, elem->list.prev);
|
|
mutex_unlock(&nf_hook_mutex);
|
|
#ifdef CONFIG_NETFILTER_INGRESS
|
|
if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
|
|
net_inc_ingress_queue();
|
|
#endif
|
|
#ifdef HAVE_JUMP_LABEL
|
|
static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
|
|
#endif
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(nf_register_net_hook);
|
|
|
|
void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
|
|
{
|
|
struct list_head *nf_hook_list;
|
|
struct nf_hook_ops *elem;
|
|
|
|
nf_hook_list = find_nf_hook_list(net, reg);
|
|
if (!nf_hook_list)
|
|
return;
|
|
|
|
mutex_lock(&nf_hook_mutex);
|
|
list_for_each_entry(elem, nf_hook_list, list) {
|
|
if ((reg->hook == elem->hook) &&
|
|
(reg->dev == elem->dev) &&
|
|
(reg->owner == elem->owner) &&
|
|
(reg->priv == elem->priv) &&
|
|
(reg->pf == elem->pf) &&
|
|
(reg->hooknum == elem->hooknum) &&
|
|
(reg->priority == elem->priority)) {
|
|
list_del_rcu(&elem->list);
|
|
break;
|
|
}
|
|
}
|
|
mutex_unlock(&nf_hook_mutex);
|
|
if (&elem->list == nf_hook_list) {
|
|
WARN(1, "nf_unregister_net_hook: hook not found!\n");
|
|
return;
|
|
}
|
|
#ifdef CONFIG_NETFILTER_INGRESS
|
|
if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
|
|
net_dec_ingress_queue();
|
|
#endif
|
|
#ifdef HAVE_JUMP_LABEL
|
|
static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
|
|
#endif
|
|
synchronize_net();
|
|
nf_queue_nf_hook_drop(net, elem);
|
|
kfree(elem);
|
|
}
|
|
EXPORT_SYMBOL(nf_unregister_net_hook);
|
|
|
|
int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg,
|
|
unsigned int n)
|
|
{
|
|
unsigned int i;
|
|
int err = 0;
|
|
|
|
for (i = 0; i < n; i++) {
|
|
err = nf_register_net_hook(net, ®[i]);
|
|
if (err)
|
|
goto err;
|
|
}
|
|
return err;
|
|
|
|
err:
|
|
if (i > 0)
|
|
nf_unregister_net_hooks(net, reg, i);
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(nf_register_net_hooks);
|
|
|
|
void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
|
|
unsigned int n)
|
|
{
|
|
while (n-- > 0)
|
|
nf_unregister_net_hook(net, ®[n]);
|
|
}
|
|
EXPORT_SYMBOL(nf_unregister_net_hooks);
|
|
|
|
static LIST_HEAD(nf_hook_list);
|
|
|
|
int nf_register_hook(struct nf_hook_ops *reg)
|
|
{
|
|
struct net *net, *last;
|
|
int ret;
|
|
|
|
rtnl_lock();
|
|
for_each_net(net) {
|
|
ret = nf_register_net_hook(net, reg);
|
|
if (ret && ret != -ENOENT)
|
|
goto rollback;
|
|
}
|
|
list_add_tail(®->list, &nf_hook_list);
|
|
rtnl_unlock();
|
|
|
|
return 0;
|
|
rollback:
|
|
last = net;
|
|
for_each_net(net) {
|
|
if (net == last)
|
|
break;
|
|
nf_unregister_net_hook(net, reg);
|
|
}
|
|
rtnl_unlock();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(nf_register_hook);
|
|
|
|
void nf_unregister_hook(struct nf_hook_ops *reg)
|
|
{
|
|
struct net *net;
|
|
|
|
rtnl_lock();
|
|
list_del(®->list);
|
|
for_each_net(net)
|
|
nf_unregister_net_hook(net, reg);
|
|
rtnl_unlock();
|
|
}
|
|
EXPORT_SYMBOL(nf_unregister_hook);
|
|
|
|
int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n)
|
|
{
|
|
unsigned int i;
|
|
int err = 0;
|
|
|
|
for (i = 0; i < n; i++) {
|
|
err = nf_register_hook(®[i]);
|
|
if (err)
|
|
goto err;
|
|
}
|
|
return err;
|
|
|
|
err:
|
|
if (i > 0)
|
|
nf_unregister_hooks(reg, i);
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(nf_register_hooks);
|
|
|
|
void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n)
|
|
{
|
|
while (n-- > 0)
|
|
nf_unregister_hook(®[n]);
|
|
}
|
|
EXPORT_SYMBOL(nf_unregister_hooks);
|
|
|
|
unsigned int nf_iterate(struct list_head *head,
|
|
struct sk_buff *skb,
|
|
struct nf_hook_state *state,
|
|
struct nf_hook_ops **elemp)
|
|
{
|
|
unsigned int verdict;
|
|
|
|
/*
|
|
* The caller must not block between calls to this
|
|
* function because of risk of continuing from deleted element.
|
|
*/
|
|
list_for_each_entry_continue_rcu((*elemp), head, list) {
|
|
if (state->thresh > (*elemp)->priority)
|
|
continue;
|
|
|
|
/* Optimization: we don't need to hold module
|
|
reference here, since function can't sleep. --RR */
|
|
repeat:
|
|
verdict = (*elemp)->hook(*elemp, skb, state);
|
|
if (verdict != NF_ACCEPT) {
|
|
#ifdef CONFIG_NETFILTER_DEBUG
|
|
if (unlikely((verdict & NF_VERDICT_MASK)
|
|
> NF_MAX_VERDICT)) {
|
|
NFDEBUG("Evil return from %p(%u).\n",
|
|
(*elemp)->hook, state->hook);
|
|
continue;
|
|
}
|
|
#endif
|
|
if (verdict != NF_REPEAT)
|
|
return verdict;
|
|
goto repeat;
|
|
}
|
|
}
|
|
return NF_ACCEPT;
|
|
}
|
|
|
|
|
|
/* Returns 1 if okfn() needs to be executed by the caller,
|
|
* -EPERM for NF_DROP, 0 otherwise. */
|
|
int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state)
|
|
{
|
|
struct nf_hook_ops *elem;
|
|
unsigned int verdict;
|
|
int ret = 0;
|
|
|
|
/* We may already have this, but read-locks nest anyway */
|
|
rcu_read_lock();
|
|
|
|
elem = list_entry_rcu(state->hook_list, struct nf_hook_ops, list);
|
|
next_hook:
|
|
verdict = nf_iterate(state->hook_list, skb, state, &elem);
|
|
if (verdict == NF_ACCEPT || verdict == NF_STOP) {
|
|
ret = 1;
|
|
} else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
|
|
kfree_skb(skb);
|
|
ret = NF_DROP_GETERR(verdict);
|
|
if (ret == 0)
|
|
ret = -EPERM;
|
|
} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
|
|
int err = nf_queue(skb, elem, state,
|
|
verdict >> NF_VERDICT_QBITS);
|
|
if (err < 0) {
|
|
if (err == -ECANCELED)
|
|
goto next_hook;
|
|
if (err == -ESRCH &&
|
|
(verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
|
|
goto next_hook;
|
|
kfree_skb(skb);
|
|
}
|
|
}
|
|
rcu_read_unlock();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(nf_hook_slow);
|
|
|
|
|
|
int skb_make_writable(struct sk_buff *skb, unsigned int writable_len)
|
|
{
|
|
if (writable_len > skb->len)
|
|
return 0;
|
|
|
|
/* Not exclusive use of packet? Must copy. */
|
|
if (!skb_cloned(skb)) {
|
|
if (writable_len <= skb_headlen(skb))
|
|
return 1;
|
|
} else if (skb_clone_writable(skb, writable_len))
|
|
return 1;
|
|
|
|
if (writable_len <= skb_headlen(skb))
|
|
writable_len = 0;
|
|
else
|
|
writable_len -= skb_headlen(skb);
|
|
|
|
return !!__pskb_pull_tail(skb, writable_len);
|
|
}
|
|
EXPORT_SYMBOL(skb_make_writable);
|
|
|
|
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
|
|
/* This does not belong here, but locally generated errors need it if connection
|
|
tracking in use: without this, connection may not be in hash table, and hence
|
|
manufactured ICMP or RST packets will not be associated with it. */
|
|
void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *)
|
|
__rcu __read_mostly;
|
|
EXPORT_SYMBOL(ip_ct_attach);
|
|
|
|
void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb)
|
|
{
|
|
void (*attach)(struct sk_buff *, const struct sk_buff *);
|
|
|
|
if (skb->nfct) {
|
|
rcu_read_lock();
|
|
attach = rcu_dereference(ip_ct_attach);
|
|
if (attach)
|
|
attach(new, skb);
|
|
rcu_read_unlock();
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(nf_ct_attach);
|
|
|
|
void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly;
|
|
EXPORT_SYMBOL(nf_ct_destroy);
|
|
|
|
void nf_conntrack_destroy(struct nf_conntrack *nfct)
|
|
{
|
|
void (*destroy)(struct nf_conntrack *);
|
|
|
|
rcu_read_lock();
|
|
destroy = rcu_dereference(nf_ct_destroy);
|
|
BUG_ON(destroy == NULL);
|
|
destroy(nfct);
|
|
rcu_read_unlock();
|
|
}
|
|
EXPORT_SYMBOL(nf_conntrack_destroy);
|
|
|
|
struct nfq_ct_hook __rcu *nfq_ct_hook __read_mostly;
|
|
EXPORT_SYMBOL_GPL(nfq_ct_hook);
|
|
|
|
struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook __read_mostly;
|
|
EXPORT_SYMBOL_GPL(nfq_ct_nat_hook);
|
|
|
|
#endif /* CONFIG_NF_CONNTRACK */
|
|
|
|
#ifdef CONFIG_NF_NAT_NEEDED
|
|
void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
|
|
EXPORT_SYMBOL(nf_nat_decode_session_hook);
|
|
#endif
|
|
|
|
static int nf_register_hook_list(struct net *net)
|
|
{
|
|
struct nf_hook_ops *elem;
|
|
int ret;
|
|
|
|
rtnl_lock();
|
|
list_for_each_entry(elem, &nf_hook_list, list) {
|
|
ret = nf_register_net_hook(net, elem);
|
|
if (ret && ret != -ENOENT)
|
|
goto out_undo;
|
|
}
|
|
rtnl_unlock();
|
|
return 0;
|
|
|
|
out_undo:
|
|
list_for_each_entry_continue_reverse(elem, &nf_hook_list, list)
|
|
nf_unregister_net_hook(net, elem);
|
|
rtnl_unlock();
|
|
return ret;
|
|
}
|
|
|
|
static void nf_unregister_hook_list(struct net *net)
|
|
{
|
|
struct nf_hook_ops *elem;
|
|
|
|
rtnl_lock();
|
|
list_for_each_entry(elem, &nf_hook_list, list)
|
|
nf_unregister_net_hook(net, elem);
|
|
rtnl_unlock();
|
|
}
|
|
|
|
static int __net_init netfilter_net_init(struct net *net)
|
|
{
|
|
int i, h, ret;
|
|
|
|
for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) {
|
|
for (h = 0; h < NF_MAX_HOOKS; h++)
|
|
INIT_LIST_HEAD(&net->nf.hooks[i][h]);
|
|
}
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter",
|
|
net->proc_net);
|
|
if (!net->nf.proc_netfilter) {
|
|
if (!net_eq(net, &init_net))
|
|
pr_err("cannot create netfilter proc entry");
|
|
|
|
return -ENOMEM;
|
|
}
|
|
#endif
|
|
ret = nf_register_hook_list(net);
|
|
if (ret)
|
|
remove_proc_entry("netfilter", net->proc_net);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void __net_exit netfilter_net_exit(struct net *net)
|
|
{
|
|
nf_unregister_hook_list(net);
|
|
remove_proc_entry("netfilter", net->proc_net);
|
|
}
|
|
|
|
static struct pernet_operations netfilter_net_ops = {
|
|
.init = netfilter_net_init,
|
|
.exit = netfilter_net_exit,
|
|
};
|
|
|
|
int __init netfilter_init(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = register_pernet_subsys(&netfilter_net_ops);
|
|
if (ret < 0)
|
|
goto err;
|
|
|
|
ret = netfilter_log_init();
|
|
if (ret < 0)
|
|
goto err_pernet;
|
|
|
|
return 0;
|
|
err_pernet:
|
|
unregister_pernet_subsys(&netfilter_net_ops);
|
|
err:
|
|
return ret;
|
|
}
|